© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97189
    Prev
    Next
    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    al
    -1.21
    ual
    -0.66
    ed
    -0.61
    raising
    -0.57
    ground
    -0.56
     France
    -0.55
    ival
    -0.53
    es
    -0.49
    almo
    -0.49
    ic
    -0.49
    POSITIVE LOGITS
    ChildScrollView
    0.79
    bewerken
    0.77
    GraphicsUnit
    0.75
    تقاوى
    0.73
     Мексичка
    0.68
    BASEPATH
    0.66
    SBATCH
    0.66
    AndEndTag
    0.66
     myſelf
    0.65
    AddHtmlAttribute
    0.65
    Activations Density 0.209%

    No Known Activations